DeepInfra

About DeepInfra

DeepInfra offers cost-effective, scalable, easy-to-deploy, and production-ready machine-learning models and infrastructures for deep-learning models.

Website ↗Documentation ↗

Source ↗ · 2026-11-12T03:22:34.866718324Z

Service status

operational

Published API and monitored model status; excludes the website and unmonitored deployments

Official status page ↗

105 indexed models

105 matching models

bria: Remove Background

cloudflareWorkersAI/bria/remove-background

Bria's RMBG 2.0 model removes the background from an image and returns a PNG cutout with a transparent background. Partial transparency from the input's alpha channel is kept by default.

Input modalities
image, text
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

Bytedance Seed 1.8

vercelAIGatewayCatalog/bytedance/seed-1.8

Bytedance Seed 1.8 features stronger multimodal understanding and agent capabilities. The model delivers superior performance across a wide range of complex real-world tasks, helping enterprises create greater value.

Context window
256,000
Maximum output
64,000
Input modalities
text, image
Output modalities
text

Inference prices

  • Published price : $0.25 / input_tokens_per_million · deepInfra ↗
  • Published price : $2.00 / output_tokens_per_million · deepInfra ↗

bytedance: Seedream 4.5

cloudflareWorkersAI/bytedance/seedream-4.5

Seedream 4.5 builds on 4.0 with multi-reference image support, batch generation, and sequential image generation.

Input modalities
text
Output modalities
image
Capabilities
imageOutput

Canopy Labs: Orpheus 3B

canopylabs/orpheus-3b-0.1-ft

Orpheus 3B is an English text-to-speech model from Canopy Labs, fine-tuned for natural prosody and expressive delivery. It offers 7 preset voices and is suited for narration, voice assistants, and interactive applications where naturalistic speech is a priority.

Context window
4,096
Input modalities
text
Output modalities
speech
Capabilities
speechOutput

Cloudflare: Clef

cloudflare/clef

Clef is Cloudflare's open-source 27B multimodal decision model, a fine-tune of Qwen3.8-27B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every questi

Context window
65,537
Input modalities
text, image
Output modalities
decisions
Capabilities
decisions, multimodal, visionInput

Inference prices

  • Published price : $0.24 / input_tokens_per_million · deepInfra ↗
  • Published price : $0.00 / output_tokens_per_million · deepInfra ↗

Cloudflare: Clef Flash

cloudflare/clef-flash

Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowe

Context window
24,576
Input modalities
text, image
Output modalities
decisions
Capabilities
decisions, multimodal, visionInput

Inference prices

  • Published price : $0.04 / input_tokens_per_million · deepInfra ↗
  • Published price : $0.00 / output_tokens_per_million · deepInfra ↗

cognitivecomputations/dolphin-2.9.1-llama-3-70b

azureFoundry/HuggingFace/cognitivecomputations-dolphin-2.9.1-llama-3-70b@1

`cognitivecomputations/dolphin-2.9.1-llama-3-70b` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-70b

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v2: 25.534%

Inference prices

  • Published price : $0.35 / input_tokens_per_million · deepInfra ↗
  • Published price : $0.40 / output_tokens_per_million · deepInfra ↗

Cosmos3-Super

vertexAI/publishers/nvidia/models/cosmos3-nano@cosmos3-super

Input modalities
text
Output modalities
text
Capabilities
audioInput, imageOutput, multimodal, videoOutput, visionInput

DeepSeek: R1 0528

deepseek/deepseek-r1-0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.

Context window
163,840
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 13.1
  • HELM Capabilities: 66.592%
  • OpenCompass LLM: 83.5%
  • OpenRouter Benchmarks: 79.586%

Inference prices

  • Published price : $0.50 / input_tokens_per_million · deepInfra ↗
  • Published price : $2.15 / output_tokens_per_million · deepInfra ↗

FLUX.2-dev

blackForestLabs/flux.2-dev

State-of the art in-context image generation and editing - combine text and images for precise, coherent

Input modalities
image
Output modalities
image
Capabilities
imageOutput, visionInput

GLM 4.7 Flash

awsBedrock/zai.glm-4.7-flash

Input modalities
text
Output modalities
text

Inference prices

  • Published price : $0.06 / input_tokens_per_million · deepInfra ↗
  • Published price : $0.40 / output_tokens_per_million · deepInfra ↗

hexgrad: Kokoro 82M

hexgrad/kokoro-82m

Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese) using 54 preset voices organized by language and gender. At

Context window
4,096
Input modalities
text
Output modalities
speech
Capabilities
speechOutput

Intfloat: Multilingual-E5-Large

intfloat/multilingual-e5-large-20251117

The multilingual-e5-large embedding model encodes sentences, paragraphs, and documents across over 90 languages into a 1024-dimensional dense vector space, delivering robust semantic embeddings optimized for multilingual retrieval, cross-language similarity, and large-scale data

Context window
512
Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Benchmarks

  • MTEB: 69.534%

Inference prices

  • Published price : $0.01 / input_tokens_per_million · deepInfra ↗

inworld: Inworld TTS 1.5 Max

cloudflareWorkersAI/inworld/tts-1.5-max

Highest-quality text-to-speech with under 200ms latency, emotion control, and 15-language support.

Input modalities
text
Output modalities
speech
Capabilities
speechOutput

inworld: Inworld TTS 1.5 Mini

cloudflareWorkersAI/inworld/tts-1.5-mini

Ultra-fast, cost-efficient text-to-speech with approximately 120ms latency and 15-language support.

Input modalities
text
Output modalities
speech
Capabilities
speechOutput

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace